Learning Filter Basis for Convolutional Neural Network Compression

by   Yawei Li, et al.
ETH Zurich

Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy.


page 6

page 13

page 14


Parameter-Free Channel Attention for Image Classification and Super-Resolution

The channel attention mechanism is a useful technique widely employed in...

LinearConv: Regenerating Redundancy in Convolution Filters as Linear Combinations for Parameter Reduction

Convolutional Neural Networks (CNNs) show state-of-the-art performance i...

Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are well established models capable...

Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs

In this paper, we propose a fixed convolutional layer with an order of s...

Resolution learning in deep convolutional networks using scale-space theory

Resolution in deep convolutional neural networks (CNNs) is typically bou...

Training CNNs with Low-Rank Filters for Efficient Image Classification

We propose a new method for creating computationally efficient convoluti...

Hybrid Cosine Based Convolutional Neural Networks

Convolutional neural networks (CNNs) have demonstrated their capability ...

Code Repositories


Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression. CVPR2020.

view repo


Pytorch implemenation of "Learning Filter Basis for Convolutional Neural Network Compression" ICCV2019

view repo

Please sign up or login with your details

Forgot password? Click here to reset